Matthew R. Glickman

Preparing for the aftermath: Using emotional agents in game-based training for disaster response

Ground truth, a training game developed by Sandia National Laboratories in partnership with the University of Southern California GamePipe Lab, puts a player in the role of an incident commander working with teammate agents to respond to urban threats. These agents simulate certain emotions that a responder may feel during this high-stress situation. We construct psychology-plausible models compliant with the Sandia Human Embodiment and Representation Cognitive Architecture (SHERCA) that are run on the sandia cognitive runtime engine with active memory (SCREAM) software. SCREAMs computational representations for modeling human decision-making combine aspects of ANNs and fuzzy logic networks. This paper gives an overview of ground truth and discusses the adaptation of the SHERCA and SCREAM into the game. We include a semiformal description of SCREAM.

Foundations to the unified psycho-cognitive engine.

This document outlines the key features of the SNL psychological engine. The engine is designed to be a generic presentation of cognitive entities interacting among themselves and with the external world. The engine combines the most accepted theories of behavioral psychology with those of behavioral economics to produce a unified simulation of human response from stimuli through executed behavior. The engine explicitly recognizes emotive and reasoned contributions to behavior and simulates the dynamics associated with cue processing, learning, and choice selection. Most importantly, the model parameterization can come from available media or survey information, as well subject-matter-expert information. The framework design allows the use of uncertainty quantification and sensitivity analysis to manage confidence in using the analysis results for intervention decisions.

Modeling Populations of Interest in Order to Simulate Cultural Response to Influence Activities

This paper describes an effort by Sandia National Laboratories to model and simulate populations of specific countries of interest as well as the population’s primary influencers, such as government and military leaders. To accomplish this, high definition cognition models are being coupled with an aggregate model of a population to produce a prototype, dynamic cultural representation of a specific country of interest. The objective is to develop a systems-level, intrinsic security capability that will allow analysts to better assess the potential actions, counteractions, and influence of powerful individuals within a country of interest before, during, and after an US initiated event. 1 Societal Assessment Capability The United States is finding itself increasingly engaged in the development of unconventional partnerships that require a variety of non-traditional activities to better support political and economic stability in regions of interest. Unfortunately, there is no effective means to adequately forecast and assess how both individual leaders, and the people they influence, will behave with regard to possible US policies and actions. It is asserted here that an accurate characterization of a society must represent this interaction between people under control, those influencing power, and external variables, such as US actions or oil revenue variation (in counties dependent on oil). While assessment tools have modeled and simulated societies, they have, thus far, been limited to gross behavioral models. Furthermore, no existing macroeconomic or societal model addresses security dynamics or coordinated multiple kinetic and non-kinetic interventions. We believe that the phenomena that maintain or transition dictatorship and democracy have recently become understandable enough to pose testable hypotheses amenable to simulation. As such, the ability to address intervention dynamics and unintended, higher order consequences is a key goal of this work. In pursuit of this goal, Sandia National Laboratories (Sandia) has developed a prototype societal assessment capability that assists in the behavioral influence analysis of foreign targets of interest. The objective of the described work is to develop a systems-level capability that will allow analysts to better assess potential actions and counter-actions of individuals interacting within a foreign country of interest before, during, and after an US initiated event. The assessment is designed to address the dynamics that drive stability and instability. Specifically, it is designed to: (1) assess adversarial choice options that allow analysts to pose “what-if” queries concerning hypothetical policy and/or military initiatives to help determine how and why a population may react to a specific event, leader, or operation across time, (2) assess potential blind spots by providing analysts with the ability to better understand higher order interaction effects between leaders and local societies and how allegiances are formed and changed over time, (3) perform risk analysis by determining the limiting assumptions and unknowns for the successful outcome, and (4) perform risk management by establishing whether there are delayed consequences that will require mitigation or adjustments to planning. Collectively, this type of simulation is designed to permit assessment of shaping activities and US tactics in an operational environment by creating a system that can help an analyst better understand the interaction between leaders and local societies and how allegiances are formed and changed over time. To accomplish this Sandia is utilizing its extensive technical expertise in Modeling & Simulation (M&S) to create a social simulation platform that couples HighDefinition Cognitive Models (HDCM) with a cultural, economic, and policy-based simulation. The HDCMs are purposely designed to computationally represent the mindset of specific individuals, including their cognitive perceptions, goals, emotion states, and action intentions. The actions of one HDCM can affect the mindset and actions of others, as well as the general mindset of the society in which they are situated. The society, computationally represented in this initial effort by Sandia’s Systems Dynamics-based Aggregate Societal Model (SDASM) can, in turn, affect the actions of the HDCMs (see Figure 1). The HDCM is focused on individual or smallgroup level of analysis, whereas the SDASM is focused at an aggregate level social, economic, and cultural level of analysis. These models are joined to provide a highfidelity, scaleable assessment tool of individuals, small groups, and society to produce outcome distributions investigating attitudinal and behavioral reactions to US policies for a given country, group, or ethnic region. Figure 1. A conceptual view of Sandia’s High Definition Aggregate Societal Model-

A Data-Driven Approach to Assessing Team Performance through Team Communication.

For teams working in complex task environments, instilling effective communication between team members is a primary goal during task training. Presently, responsibility for evaluating team communication abilities resides with instructors and outside observers who make qualitative assessments that are shared with the team following a training exercise. Constructing technologies to automate these assessments has historically been prohibitive for two reasons. First, the financial cost of instrumenting the environment to collect team communication data at the necessary fidelity has been too high for an operational setting. Second, past research on using team communication as a proxy for team performance assessment has relied on defining communication through traditional algorithmic design, an approach which does not properly capture the varied nature of communication strategies amongst different teams. Recent scientific research in team dynamics provides a theoretical framework leading to a data-driven solution for analyzing the effectiveness of team communication. By framing team communication as an emergent data stream from a complex system, one may employ machine learning or other statisticalanalysis tools to highlight communication patterns and variance, both shown as effective means for assessing team adaptability to novel scenarios. Furthermore, low-cost wearable computers have opened new possibilities for observing people’s interactions in natural settings to better analyze and improve team performance. We summarize research conducted in developing a data-driven approach to analyzing team communications within the context of Surfaced Piloting and Navigation (SPAN) training for submariners. Using Dynamic Bayesian Networks (DBNs), this approach created predictive models of communication patterns that emerge from the team in different contexts. Based upon data collection conducted in the lab and within live submarine crew training, our results demonstrate the robust nature of DBNs by still identifying key communication events even when teams altered their speaking patterns during these events to accommodate for novel changes in the scenario. Introduction Complex tasks that demand a coordinated effort benefit from the capacity of a team to pool resources via an exchange of information and coordinated action, though the effectiveness of a team may be contingent on a variety of factors [1]. Team effectiveness has particular impact within a military setting, as within combat situations the performance of a group has a direct bearing on the survival of the group and those dependent on them [2], situation that holds true when considering the success of naval operations [3]. In an attempt to determine the critical elements that make up an effective team in a military setting, variables related to team effectiveness have been examined from a variety of perspectives, including team cohesiveness (i.e., shared interpersonal closeness and group goal-orientation) [4], [5] collective orientation [1], shared mental models (i.e., synthesis of input from individual team members) [6], [7], [8], team selection and composition (e.g., the skills possessed by the individual team members, how long the members have been working together) [5], [6], [9], quality of decisions made by commanders [10], [11], cognitive readiness and adaptive decision making at the group level [12], training adequacy [5], the workload involved [13], and even neurophysiologic synchrony between team members, as assessed via electroencephalogram [14]. In the context of naval operations, assessment of the quality of teamwork has proven difficult, with such assessments relying on the observations of subject matter experts, skilled instructors, or a self-evaluation within teams during live or simulated exercises [3]. These judgments are subjective by their very nature, leading to a potential lack of consistency with regard to the quality of assessment. This issue has been recognized, and there have been attempts to resolve it, such as through outcome-based Copyright